| A simple framework for contrastive learning of visual representations T Chen, S Kornblith, M Norouzi, G Hinton Proceedings of the 37th International Conference on Machine Learning, 2020 | 23725 | 2020 |
| Big self-supervised models are strong semi-supervised learners T Chen, S Kornblith, K Swersky, M Norouzi, G Hinton Advances in Neural Information Processing Systems 33, 2020 | 2620 | 2020 |
| When does label smoothing help? R Müller, S Kornblith, G Hinton Advances in Neural Information Processing Systems, 2019, 2019 | 2462 | 2019 |
| Do better ImageNet models transfer better? S Kornblith, J Shlens, QV Le Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2019 | 1656 | 2019 |
| Similarity of neural network representations revisited S Kornblith, M Norouzi, H Lee, G Hinton Proceedings of the 36th International Conference on Machine Learning 97 …, 2019 | 1513 | 2019 |
| Do vision transformers see like convolutional neural networks? M Raghu, T Unterthiner, S Kornblith, C Zhang, A Dosovitskiy Advances in neural information processing systems 34, 12116-12128, 2021 | 1186 | 2021 |
| Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time M Wortsman, G Ilharco, SY Gadre, R Roelofs, R Gontijo-Lopes, ... International conference on machine learning, 23965-23998, 2022 | 922 | 2022 |
| Robust fine-tuning of zero-shot models M Wortsman, G Ilharco, JW Kim, M Li, S Kornblith, R Roelofs, RG Lopes, ... Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022 | 680 | 2022 |
| Big self-supervised models advance medical image classification S Azizi, B Mustafa, F Ryan, Z Beaver, J Freyberg, J Deaton, A Loh, ... Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021 | 644 | 2021 |
| Openflamingo: An open-source framework for training large autoregressive vision-language models A Awadalla, I Gao, J Gardner, J Hessel, Y Hanafy, W Zhu, K Marathe, ... arXiv preprint arXiv:2308.01390, 2023 | 509 | 2023 |
| The origins and prevalence of texture bias in convolutional neural networks K Hermann, T Chen, S Kornblith Advances in Neural Information Processing Systems 33, 2020 | 344 | 2020 |
| Towards generalist biomedical AI T Tu, S Azizi, D Driess, M Schaekermann, M Amin, PC Chang, A Carroll, ... NEJM AI 1 (3), AIoa2300138, 2024 | 318 | 2024 |
| Laminar recordings in frontal cortex suggest distinct layers for maintenance and control of working memory AM Bastos, R Loonis, S Kornblith, M Lundqvist, EK Miller Proceedings of the National Academy of Sciences 115 (5), 1117-1122, 2018 | 312 | 2018 |
| Synthetic data from diffusion models improves imagenet classification S Azizi, S Kornblith, C Saharia, M Norouzi, DJ Fleet arXiv preprint arXiv:2304.08466, 2023 | 306 | 2023 |
| Latency and selectivity of single neurons indicate hierarchical processing in the human medial temporal lobe F Mormann, S Kornblith, RQ Quiroga, A Kraskov, M Cerf, I Fried, C Koch Journal of neuroscience 28 (36), 8865-8872, 2008 | 301 | 2008 |
| Do wide and deep networks learn the same things? Uncovering how neural network representations vary with width and depth T Nguyen, M Raghu, S Kornblith International Conference on Learning Representations, 2021 | 298 | 2021 |
| Robust and data-efficient generalization of self-supervised machine learning for diagnostic imaging S Azizi, L Culp, J Freyberg, B Mustafa, S Baur, S Kornblith, T Chen, ... Nature Biomedical Engineering 7 (6), 756-779, 2023 | 233* | 2023 |
| A category-specific response to animals in the right human amygdala F Mormann, J Dubois, S Kornblith, M Milosavljevic, M Cerf, M Ison, ... Nature Neuroscience 14 (10), 1247-1249, 2011 | 227 | 2011 |
| Boosting contrastive self-supervised learning with false negative cancellation T Huynh, S Kornblith, MR Walter, M Maire, M Khademi Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2022 | 198 | 2022 |
| Decoder Denoising Pretraining for Semantic Segmentation EA Brempong, S Kornblith, T Chen, N Parmar, M Minderer, M Norouzi Transactions on Machine Learning Research, 2022 | 152* | 2022 |
Mohammad NorouziIdeogramEmail verificata su ideogram.ai